© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56846
    Prev
    Next
    INDEX
    Explanations

    mino acid, Con Indy, invention is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eth
    -0.07
    ub
    -0.06
    rence
    -0.06
    *******
    -0.06
    credi
    -0.06
     pr
    -0.06
    å·¥ä½ľæĸ¹æ¡Ī
    -0.06
    ag
    -0.06
    å»ī
    -0.06
    å®Ĺ亲
    -0.06
    POSITIVE LOGITS
    มวล
    0.08
    æĮĿ
    0.08
    幡
    0.07
    ç¥Ŀ
    0.07
    мбÑĥ
    0.07
    çĮ¬
    0.07
    erse
    0.07
    кеÑĢа
    0.07
    çµ®
    0.07
    usher
    0.07
    Activations Density 0.009%

    No Known Activations